Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 137
    Prev
    Next
    INDEX
    Explanations

    email address patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.79
     مشين
    -0.68
    లాలు
    -0.67
    tanleria
    -0.63
    WebVitals
    -0.62
    lobo
    -0.62
    Vorlage
    -0.61
    ագրություններ
    -0.61
    ++
    
    -0.60
     Wikiseite
    -0.58
    POSITIVE LOGITS
    InSection
    0.63
     predeceased
    0.49
     shutters
    0.44
     antifungal
    0.42
     namesake
    0.42
     nativo
    0.42
    ########.
    0.41
    3
    0.40
    1
    0.39
     grafts
    0.39
    Activations Density 0.167%

    No Known Activations